Create app.py

app.py

@@ -0,0 +1,81 @@
+import gradio as gr
+import pandas as pd
+
+
+from transformers import pipeline
+
+# model_name="aminghias/distilbert-base-uncased-finetuned-imdb"
+
+# mask_filler = pipeline(
+#     "fill-mask", model=model_name
+# )
+
+pipe = pipeline("fill-mask", model="aminghias/Clinical-BERT-finetuned ")
+pipe2 = pipeline("fill-mask", model="emilyalsentzer/Bio_ClinicalBERT")
+pipe3= pipeline("fill-mask", model="medicalai/ClinicalBERT")
+
+
+
+
+
+def predict(text):
+
+    pred1 = pipe(text)
+    pred2 = pipe2(text)
+    pred3= pipe3(text)
+    
+    df_sum=pd.DataFrame(pred1)
+    
+    df_sum
+    df_sum2=pd.DataFrame(pred2)
+    
+    df_sum2
+
+    df_sum3= pd.DataFrame(pred3)
+    
+    # # join the two dataframes on token do outer join
+    
+    df_join=pd.merge(df_sum,df_sum2,on='token_str',how='outer')
+    df_join=pd.merge(df_sum3,df_join,on='token_str',how='outer')
+    
+    df_join
+    df_join['sum_sequence']=df_join['sequence_x'].fillna(df_join['sequence_y'])
+    df_join['sum_sequence']=df_join['sum_sequence'].fillna(df_join['sequence'])
+    df_join=df_join.fillna(0)
+    df_join['score_sum']=(df_join['score_x']+df_join['score_y']+df_join['score'])/3
+    
+    df_join=df_join.sort_values(by='score_sum',ascending=False)
+    df_join=df_join.reset_index(drop=True)
+    # df_join=df_join.dropna()
+    # df_join=df_join.fillna(0)
+    df=df_join.copy()
+    df_join=df_join[['score_sum','token_str','sum_sequence']]
+
+    # gr.Interface(fn=lambda: df_join, inputs=None, outputs=gr.Dataframe(headers=df_join.columns)).launch()
+    
+    # print(df_join)
+    # df_join['sum_sequence'][0]
+    return (df['sum_sequence'][0],df_join)
+
+    
+  # return (pipe(text)[0]['sequence'],pipe2(text)[0]['sequence'])
+    
+demo = gr.Interface(
+  fn=predict, 
+  inputs='text',
+  # outputs='text',
+  outputs=['text','text'],
+    # outputs='text','text',
+
+     # outputs=gr.Dataframe(headers=['title', 'author', 'text']), allow_flagging='never')
+
+  title="Filling Missing Clinincal/Medical Data ",
+    examples=[ ['The  high blood pressure was due to [MASK]  which is critical.'],
+              ['The [MASK] caused headace and dizziness.']
+             ],
+    description="This application fills any missing words in the medical domain",
+  # fn=lambda: df, inputs=None, outputs=gr.Dataframe(headers=df_join.columns)
+ # fn = infer, inputs = inputs, outputs = outputs, examples = [[df_join.head()]]
+)
+
+demo.launch()